manu commited on
Commit
df35231
1 Parent(s): 38d41c8

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vidore/colqwen2-base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vidore/colqwen2-base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": "gaussian",
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
23
+ "task_type": "FEATURE_EXTRACTION",
24
+ "use_dora": false,
25
+ "use_rslora": false
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79486a855077e5b6fef0bc268764152618fa1f3bb04792f9d8e6d32c7b72237
3
+ size 74018232
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
git_hash.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 25e0153080178406a6708e03c092dc56b5e482d2
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "ColQwen2Processor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.69927, "ndcg_at_3": 0.78159, "ndcg_at_5": 0.80664, "ndcg_at_10": 0.82137, "ndcg_at_20": 0.82457, "ndcg_at_50": 0.82793, "ndcg_at_100": 0.8296, "map_at_1": 0.69927, "map_at_3": 0.76225, "map_at_5": 0.77616, "map_at_10": 0.78248, "map_at_20": 0.78342, "map_at_50": 0.78395, "map_at_100": 0.7841, "recall_at_1": 0.69927, "recall_at_3": 0.83718, "recall_at_5": 0.89793, "recall_at_10": 0.94228, "recall_at_20": 0.95443, "recall_at_50": 0.97145, "recall_at_100": 0.98177, "precision_at_1": 0.69927, "precision_at_3": 0.27906, "precision_at_5": 0.17959, "precision_at_10": 0.09423, "precision_at_20": 0.04772, "precision_at_50": 0.01943, "precision_at_100": 0.00982, "mrr_at_1": 0.6974483596597812, "mrr_at_3": 0.761543134872418, "mrr_at_5": 0.7746658566221142, "mrr_at_10": 0.7814586587976624, "mrr_at_20": 0.7824191336998677, "mrr_at_50": 0.7829654852280344, "mrr_at_100": 0.7831078050872305, "naucs_at_1_max": 0.25090705114736095, "naucs_at_1_std": -0.2940533354269669, "naucs_at_1_diff1": 0.8007724165936554, "naucs_at_3_max": 0.3012096695305833, "naucs_at_3_std": -0.26907262221168937, "naucs_at_3_diff1": 0.694047297263378, "naucs_at_5_max": 0.38315408734215384, "naucs_at_5_std": -0.11705503964351588, "naucs_at_5_diff1": 0.6525965995076792, "naucs_at_10_max": 0.5023489181540841, "naucs_at_10_std": 0.07188093987240221, "naucs_at_10_diff1": 0.6035975824693318, "naucs_at_20_max": 0.4924317060595406, "naucs_at_20_std": 0.20348352545042372, "naucs_at_20_diff1": 0.564375594315046, "naucs_at_50_max": 0.5257178180099493, "naucs_at_50_std": 0.4387361821625485, "naucs_at_50_diff1": 0.5178667258065841, "naucs_at_100_max": 0.5515774783565448, "naucs_at_100_std": 0.4959428152129429, "naucs_at_100_diff1": 0.48973397557707626}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.76, "ndcg_at_3": 0.86202, "ndcg_at_5": 0.87881, "ndcg_at_10": 0.88485, "ndcg_at_20": 0.88485, "ndcg_at_50": 0.88707, "ndcg_at_100": 0.88707, "map_at_1": 0.76, "map_at_3": 0.83833, "map_at_5": 0.84783, "map_at_10": 0.85008, "map_at_20": 0.85008, "map_at_50": 0.85054, "map_at_100": 0.85054, "recall_at_1": 0.76, "recall_at_3": 0.93, "recall_at_5": 0.97, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.76, "precision_at_3": 0.31, "precision_at_5": 0.194, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.77, "mrr_at_3": 0.845, "mrr_at_5": 0.8545, "mrr_at_10": 0.85675, "mrr_at_20": 0.85675, "mrr_at_50": 0.8572045454545454, "mrr_at_100": 0.8572045454545454, "naucs_at_1_max": -0.12777970061434624, "naucs_at_1_std": -0.4984857662023017, "naucs_at_1_diff1": 0.6933243921432896, "naucs_at_3_max": 0.5858343337334906, "naucs_at_3_std": -0.004468454048285659, "naucs_at_3_diff1": 0.6212484993997599, "naucs_at_5_max": 0.6101774042950485, "naucs_at_5_std": 0.0704948646125114, "naucs_at_5_diff1": 0.7587924058512269, "naucs_at_10_max": 0.5541549953314738, "naucs_at_10_std": 0.5541549953314738, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.5541549953314738, "naucs_at_20_std": 0.5541549953314738, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.99, "ndcg_at_3": 0.995, "ndcg_at_5": 0.995, "ndcg_at_10": 0.995, "ndcg_at_20": 0.995, "ndcg_at_50": 0.995, "ndcg_at_100": 0.995, "map_at_1": 0.99, "map_at_3": 0.99333, "map_at_5": 0.99333, "map_at_10": 0.99333, "map_at_20": 0.99333, "map_at_50": 0.99333, "map_at_100": 0.99333, "recall_at_1": 0.99, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.99, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.99, "mrr_at_3": 0.9933333333333333, "mrr_at_5": 0.9933333333333333, "mrr_at_10": 0.9933333333333333, "mrr_at_20": 0.9933333333333333, "mrr_at_50": 0.9933333333333333, "mrr_at_100": 0.9933333333333333, "naucs_at_1_max": 0.8692810457516276, "naucs_at_1_std": -0.17133520074696149, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.98155, "ndcg_at_5": 0.98155, "ndcg_at_10": 0.98155, "ndcg_at_20": 0.98155, "ndcg_at_50": 0.98155, "ndcg_at_100": 0.98155, "map_at_1": 0.95, "map_at_3": 0.975, "map_at_5": 0.975, "map_at_10": 0.975, "map_at_20": 0.975, "map_at_50": 0.975, "map_at_100": 0.975, "recall_at_1": 0.95, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.97, "mrr_at_3": 0.985, "mrr_at_5": 0.985, "mrr_at_10": 0.985, "mrr_at_20": 0.985, "mrr_at_50": 0.985, "mrr_at_100": 0.985, "naucs_at_1_max": 0.30924369747899044, "naucs_at_1_std": -0.1360410830999049, "naucs_at_1_diff1": 0.9444444444444438, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.82, "ndcg_at_3": 0.8565, "ndcg_at_5": 0.8719, "ndcg_at_10": 0.8816, "ndcg_at_20": 0.88566, "ndcg_at_50": 0.89002, "ndcg_at_100": 0.89133, "map_at_1": 0.82, "map_at_3": 0.84767, "map_at_5": 0.85607, "map_at_10": 0.86007, "map_at_20": 0.86119, "map_at_50": 0.86189, "map_at_100": 0.86201, "recall_at_1": 0.82, "recall_at_3": 0.882, "recall_at_5": 0.92, "recall_at_10": 0.95, "recall_at_20": 0.966, "recall_at_50": 0.988, "recall_at_100": 0.996, "precision_at_1": 0.82, "precision_at_3": 0.294, "precision_at_5": 0.184, "precision_at_10": 0.095, "precision_at_20": 0.0483, "precision_at_50": 0.01976, "precision_at_100": 0.00996, "mrr_at_1": 0.818, "mrr_at_3": 0.847, "mrr_at_5": 0.8549, "mrr_at_10": 0.8590880952380953, "mrr_at_20": 0.8602139921739768, "mrr_at_50": 0.8608936438058804, "mrr_at_100": 0.8610132721450209, "naucs_at_1_max": 0.8093071924220723, "naucs_at_1_std": -0.15325476374049982, "naucs_at_1_diff1": 0.9121599295076548, "naucs_at_3_max": 0.8687610005005734, "naucs_at_3_std": -0.10365902888791888, "naucs_at_3_diff1": 0.9062232556637445, "naucs_at_5_max": 0.8757002801120448, "naucs_at_5_std": -0.057691409897293336, "naucs_at_5_diff1": 0.8769257703081252, "naucs_at_10_max": 0.8769374416433241, "naucs_at_10_std": 0.07971988795517813, "naucs_at_10_diff1": 0.8788982259570494, "naucs_at_20_max": 0.8661229197561396, "naucs_at_20_std": 0.04668534080298997, "naucs_at_20_diff1": 0.8863074641621352, "naucs_at_50_max": 0.9074074074074128, "naucs_at_50_std": 0.08784624961095401, "naucs_at_50_diff1": 0.9101307189542546, "naucs_at_100_max": 1.0, "naucs_at_100_std": -0.29878618113917615, "naucs_at_100_diff1": 0.8611111111111168}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.5388, "ndcg_at_3": 0.59518, "ndcg_at_5": 0.61331, "ndcg_at_10": 0.63493, "ndcg_at_20": 0.64571, "ndcg_at_50": 0.66094, "ndcg_at_100": 0.66706, "map_at_1": 0.5388, "map_at_3": 0.58167, "map_at_5": 0.59165, "map_at_10": 0.60065, "map_at_20": 0.60367, "map_at_50": 0.60623, "map_at_100": 0.60677, "recall_at_1": 0.5388, "recall_at_3": 0.63415, "recall_at_5": 0.67849, "recall_at_10": 0.74501, "recall_at_20": 0.78714, "recall_at_50": 0.86253, "recall_at_100": 0.90022, "precision_at_1": 0.5388, "precision_at_3": 0.21138, "precision_at_5": 0.1357, "precision_at_10": 0.0745, "precision_at_20": 0.03936, "precision_at_50": 0.01725, "precision_at_100": 0.009, "mrr_at_1": 0.5388026607538803, "mrr_at_3": 0.581670362158167, "mrr_at_5": 0.591869918699187, "mrr_at_10": 0.6002270087635941, "mrr_at_20": 0.6037472305777859, "mrr_at_50": 0.6061531947736035, "mrr_at_100": 0.6066866021159598, "naucs_at_1_max": 0.6889602472128592, "naucs_at_1_std": -0.1364008689785892, "naucs_at_1_diff1": 0.8930276424851852, "naucs_at_3_max": 0.6662544596828847, "naucs_at_3_std": -0.14933109624836824, "naucs_at_3_diff1": 0.8452905245514425, "naucs_at_5_max": 0.6483204948903895, "naucs_at_5_std": -0.15680650756804887, "naucs_at_5_diff1": 0.8035011466433396, "naucs_at_10_max": 0.6430340754448826, "naucs_at_10_std": -0.08243399370624406, "naucs_at_10_diff1": 0.7638350871217444, "naucs_at_20_max": 0.5999865757022875, "naucs_at_20_std": -0.07009652562261486, "naucs_at_20_diff1": 0.7423981914874048, "naucs_at_50_max": 0.5676739527242458, "naucs_at_50_std": 0.13867806923314227, "naucs_at_50_diff1": 0.7117833895641, "naucs_at_100_max": 0.6025972789679037, "naucs_at_100_std": 0.3436399076261163, "naucs_at_100_diff1": 0.6500925402658911}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.99131, "ndcg_at_5": 0.99131, "ndcg_at_10": 0.99131, "ndcg_at_20": 0.99131, "ndcg_at_50": 0.99131, "ndcg_at_100": 0.99131, "map_at_1": 0.98, "map_at_3": 0.98833, "map_at_5": 0.98833, "map_at_10": 0.98833, "map_at_20": 0.98833, "map_at_50": 0.98833, "map_at_100": 0.98833, "recall_at_1": 0.98, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.98, "mrr_at_3": 0.9883333333333333, "mrr_at_5": 0.9883333333333333, "mrr_at_10": 0.9883333333333333, "mrr_at_20": 0.9883333333333333, "mrr_at_50": 0.9883333333333333, "mrr_at_100": 0.9883333333333333, "naucs_at_1_max": 0.6381886087768457, "naucs_at_1_std": -0.514472455648931, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.86437, "ndcg_at_3": 0.90057, "ndcg_at_5": 0.91233, "ndcg_at_10": 0.91896, "ndcg_at_20": 0.921, "ndcg_at_50": 0.92312, "ndcg_at_100": 0.92379, "map_at_1": 0.86437, "map_at_3": 0.89204, "map_at_5": 0.89862, "map_at_10": 0.9014, "map_at_20": 0.90196, "map_at_50": 0.90235, "map_at_100": 0.90241, "recall_at_1": 0.86437, "recall_at_3": 0.9251, "recall_at_5": 0.95344, "recall_at_10": 0.97368, "recall_at_20": 0.98178, "recall_at_50": 0.9919, "recall_at_100": 0.99595, "precision_at_1": 0.86437, "precision_at_3": 0.30837, "precision_at_5": 0.19069, "precision_at_10": 0.09737, "precision_at_20": 0.04909, "precision_at_50": 0.01984, "precision_at_100": 0.00996, "mrr_at_1": 0.8643724696356275, "mrr_at_3": 0.8927125506072875, "mrr_at_5": 0.8992914979757085, "mrr_at_10": 0.9016748602274918, "mrr_at_20": 0.9022248835445273, "mrr_at_50": 0.9026106475419066, "mrr_at_100": 0.9026754989857776, "naucs_at_1_max": 0.6579798569725905, "naucs_at_1_std": -0.08712140791369336, "naucs_at_1_diff1": 0.9443407469406064, "naucs_at_3_max": 0.7130744631859681, "naucs_at_3_std": -0.06706146302294885, "naucs_at_3_diff1": 0.9080649742289221, "naucs_at_5_max": 0.8099526169769168, "naucs_at_5_std": 0.005146135649768734, "naucs_at_5_diff1": 0.935382109408786, "naucs_at_10_max": 0.861437319577247, "naucs_at_10_std": 0.05225263906280096, "naucs_at_10_diff1": 0.9484969923113604, "naucs_at_20_max": 0.8452245940363352, "naucs_at_20_std": 0.15182628345049073, "naucs_at_20_diff1": 0.9401180393458267, "naucs_at_50_max": 0.7864897480536438, "naucs_at_50_std": 0.6051995005869166, "naucs_at_50_diff1": 0.9305663155605097, "naucs_at_100_max": 0.9346992729675874, "naucs_at_100_std": 0.861132631121016, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.94131, "ndcg_at_5": 0.95335, "ndcg_at_10": 0.95335, "ndcg_at_20": 0.95335, "ndcg_at_50": 0.95755, "ndcg_at_100": 0.95755, "map_at_1": 0.93, "map_at_3": 0.93833, "map_at_5": 0.94483, "map_at_10": 0.94483, "map_at_20": 0.94483, "map_at_50": 0.9456, "map_at_100": 0.9456, "recall_at_1": 0.93, "recall_at_3": 0.95, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.31667, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.93, "mrr_at_3": 0.9383333333333332, "mrr_at_5": 0.9453333333333334, "mrr_at_10": 0.9453333333333334, "mrr_at_20": 0.9458333333333333, "mrr_at_50": 0.9462179487179487, "mrr_at_100": 0.9462179487179487, "naucs_at_1_max": 0.7316259837268236, "naucs_at_1_std": -0.3516073095905031, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.7690009337068138, "naucs_at_3_std": -0.5534080298786143, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.861111111111116, "naucs_at_5_std": -1.1517273576097045, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.861111111111116, "naucs_at_10_std": -1.1517273576097045, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.861111111111116, "naucs_at_20_std": -1.1517273576097045, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tabfquad_test_subsampled": {"ndcg_at_1": 0.81786, "ndcg_at_3": 0.86913, "ndcg_at_5": 0.87927, "ndcg_at_10": 0.8873, "ndcg_at_20": 0.89518, "ndcg_at_50": 0.89824, "ndcg_at_100": 0.89824, "map_at_1": 0.81786, "map_at_3": 0.85714, "map_at_5": 0.86268, "map_at_10": 0.86595, "map_at_20": 0.86798, "map_at_50": 0.86857, "map_at_100": 0.86857, "recall_at_1": 0.81786, "recall_at_3": 0.90357, "recall_at_5": 0.92857, "recall_at_10": 0.95357, "recall_at_20": 0.98571, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.81786, "precision_at_3": 0.30119, "precision_at_5": 0.18571, "precision_at_10": 0.09536, "precision_at_20": 0.04929, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.8142857142857143, "mrr_at_3": 0.8559523809523809, "mrr_at_5": 0.8614880952380952, "mrr_at_10": 0.8648398526077097, "mrr_at_20": 0.8670438372717507, "mrr_at_50": 0.8674632095661231, "mrr_at_100": 0.8674632095661231, "naucs_at_1_max": 0.5880722164938427, "naucs_at_1_std": 0.2677379817513273, "naucs_at_1_diff1": 0.8970448045757864, "naucs_at_3_max": 0.6361137047411553, "naucs_at_3_std": 0.36993809869626837, "naucs_at_3_diff1": 0.843171836635889, "naucs_at_5_max": 0.6008169934640527, "naucs_at_5_std": 0.3147525676937467, "naucs_at_5_diff1": 0.815242763772175, "naucs_at_10_max": 0.5090138619550364, "naucs_at_10_std": 0.26635782518135487, "naucs_at_10_diff1": 0.7559793148028457, "naucs_at_20_max": 0.8068394024276438, "naucs_at_20_std": 0.6692343604108401, "naucs_at_20_diff1": 0.7047152194211078, "naucs_at_50_max": 1.0, "naucs_at_50_std": 1.0, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}}
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "ColQwen2Processor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
training_config.yml ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ (): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
3
+ output_dir: !path ../../../models/colqwen2-hardneg-128-5e
4
+ processor:
5
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
6
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2Processor
7
+ pretrained_model_name_or_path: "./models/colqwen2_base" # "./models/paligemma-3b-mix-448"
8
+ # max_length: 50
9
+
10
+ model:
11
+ (): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
12
+ class_to_instanciate: !ext colpali_engine.models.ColQwen2
13
+ pretrained_model_name_or_path: "./models/colqwen2_base"
14
+ torch_dtype: !ext torch.bfloat16
15
+ use_cache: false
16
+ attn_implementation: "flash_attention_2"
17
+ # device_map: "auto"
18
+ # quantization_config:
19
+ # (): transformers.BitsAndBytesConfig
20
+ # load_in_4bit: true
21
+ # bnb_4bit_quant_type: "nf4"
22
+ # bnb_4bit_compute_dtype: "bfloat16"
23
+ # bnb_4bit_use_double_quant: true
24
+
25
+ dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set_ir_negs
26
+ eval_dataset_loader: !import ../data/test_data.yaml
27
+
28
+ # max_length: 50
29
+ run_eval: true
30
+
31
+ loss_func:
32
+ (): colpali_engine.loss.late_interaction_losses.ColbertPairwiseNegativeCELoss
33
+ in_batch_term: true
34
+ tr_args:
35
+ (): transformers.training_args.TrainingArguments
36
+ output_dir: null
37
+ overwrite_output_dir: true
38
+ num_train_epochs: 5
39
+ per_device_train_batch_size: 32
40
+ gradient_checkpointing: true
41
+ gradient_checkpointing_kwargs: {"use_reentrant": false}
42
+ # 6 x 8 gpus = 48 batch size
43
+ # gradient_accumulation_steps: 4
44
+ per_device_eval_batch_size: 32
45
+ eval_strategy: "steps"
46
+ dataloader_num_workers: 8
47
+ # bf16: true
48
+ save_steps: 500
49
+ logging_steps: 10
50
+ eval_steps: 100
51
+ warmup_steps: 100
52
+ learning_rate: 5e-4
53
+ save_total_limit: 1
54
+ # resume_from_checkpoint: true
55
+ # optim: "paged_adamw_8bit" peft_config:
56
+ peft_config:
57
+ (): peft.LoraConfig
58
+ r: 32
59
+ lora_alpha: 32
60
+ lora_dropout: 0.1
61
+ init_lora_weights: "gaussian"
62
+ bias: "none"
63
+ task_type: "FEATURE_EXTRACTION"
64
+ target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
65
+ # target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
66
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff